Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 291 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0000

Data Index: 418364 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0523. Min Act: 0.0000

Data Index: 1658380 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0464. Min Act: 0.0000

Data Index: 206955 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0479. Min Act: 0.0000

Data Index: 1813522 (The Pile)

Max Activating Token Index: 25

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1771913 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0466. Min Act: 0.0000

Data Index: 945939 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0478. Min Act: 0.0000

Data Index: 1558321 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0459. Min Act: -0.0000

Data Index: 1370750 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0451. Min Act: 0.0001

Data Index: 458509 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0430. Min Act: -0.0000

Data Index: 1092655 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0447. Min Act: 0.0000

Data Index: 486258 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0442. Min Act: -0.0000

Data Index: 561320 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0441. Min Act: 0.0000

Data Index: 3020 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0435. Min Act: -0.0000

Data Index: 1469384 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0433. Min Act: 0.0001

Data Index: 1889124 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0431. Min Act: 0.0000

Data Index: 1432214 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0432. Min Act: 0.0001

Data Index: 728747 (The Pile)

Max Activating Token Index: 63

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0431. Min Act: 0.0000

Data Index: 1296056 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0429. Min Act: 0.0001

Data Index: 642279 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0428. Min Act: 0.0000

Data Index: 336753 (The Pile)

Max Activating Token Index: 27